linux-kernel - Re: zone_reclaimable() leads to livelock in __alloc_pages

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Sun, 22 May 2016 23:17:36 +0200
From:	Oleg Nesterov <oleg@...hat.com>
To:	Tetsuo Handa <penguin-kernel@...ove.SAKURA.ne.jp>
Cc:	Andrew Morton <akpm@...ux-foundation.org>,
	Andrea Arcangeli <aarcange@...hat.com>,
	Mel Gorman <mgorman@...hsingularity.net>,
	Michal Hocko <mhocko@...nel.org>, linux-kernel@...r.kernel.org,
	linux-mm@...ck.org
Subject: Re: zone_reclaimable() leads to livelock in __alloc_pages_slowpath()

On 05/21, Tetsuo Handa wrote:
>
> On 2016/05/21 5:28, Oleg Nesterov wrote:
> > It spins in __alloc_pages_slowpath() forever, __alloc_pages_may_oom() is never
> > called, it doesn't react to SIGKILL, etc.
> >
> > This is because zone_reclaimable() is always true in shrink_zones(), and the
> > problem goes away if I comment out this code
> >
> > 	if (global_reclaim(sc) &&
> > 	    !reclaimable && zone_reclaimable(zone))
> > 		reclaimable = true;
> >
> > in shrink_zones() which otherwise returns this "true" every time, and thus
> > __alloc_pages_slowpath() always sees did_some_progress != 0.
> >
>
> Michal Hocko's OOM detection rework patchset that removes that code was sent
> to Linus 4 hours ago. ( https://marc.info/?l=linux-mm-commits&m=146378862415399 )
> Please wait for a few days and try reproducing using linux.git .

I guess you mean
http://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git/commit/mm/vmscan.c?id=fa8c5f033ebb43f925d68c29d297bafd36af7114
"mm, oom: rework oom detection"...

Yes thanks a lot Tetsuo, it should fix the problem.

Cough I can't resist I hate Michal^W the fact this was already fixed ;) Because
it took me some time to understand whats going on, initially it looked like some
subtle and hard-to-reproduce bug in userfaultfd.

Thanks!

Oleg.